Re:AllenNLP – An open-source NLP research library, built on ...
by sanxiyn on Saturday September 16, 2017 @04:57AM
(#15263686)
In "Adversarial Examples for Evaluating Reading Comprehension Systems" https://arxiv.org/abs/1707.07328, it was found that adding a single distracting sentence can lower F1 score of BiDAF (which is used in demo here) from 75.5% to 34.3% on SQuAD. In comparison, human performance goes from 92.6% to 89.2%.
[ Parent
| on HN ]
Re:AllenNLP – An open-source NLP research library, built on ...
by andrew3726 on Saturday September 16, 2017 @08:28AM
(#15264345)
There's a blog post (the morning paper) about this:
https://blog.acolyer.org/2017/09/13/adversarial-examples-for...